Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations

Xin Lv, Yuxian Gu, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu


Abstract
Multi-hop knowledge graph (KG) reasoning is an effective and explainable method for predicting the target entity via reasoning paths in query answering (QA) task. Most previous methods assume that every relation in KGs has enough triples for training, regardless of those few-shot relations which cannot provide sufficient triples for training robust reasoning models. In fact, the performance of existing multi-hop reasoning methods drops significantly on few-shot relations. In this paper, we propose a meta-based multi-hop reasoning method (Meta-KGR), which adopts meta-learning to learn effective meta parameters from high-frequency relations that could quickly adapt to few-shot relations. We evaluate Meta-KGR on two public datasets sampled from Freebase and NELL, and the experimental results show that Meta-KGR outperforms state-of-the-art methods in few-shot scenarios. In the future, our codes and datasets will also be available to provide more details.
Anthology ID:
D19-1334
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3376–3381
Language:
URL:
https://aclanthology.org/D19-1334
DOI:
10.18653/v1/D19-1334
Bibkey:
Cite (ACL):
Xin Lv, Yuxian Gu, Xu Han, Lei Hou, Juanzi Li, and Zhiyuan Liu. 2019. Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3376–3381, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations (Lv et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1334.pdf
Code
 THU-KEG/MetaKGR
Data
NELLNELL-995